Merge tag 'v5.15.60' into 5.15-2.1.x-imx

This is the 5.15.60 stable release

Signed-off-by: Daiane Angolini <daiane.angolini@foundries.io>

10 files changed, 208 insertions, 32 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 3781a7f489ef..bcaedfe60572 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -300,6 +300,7 @@
 #define X86_FEATURE_RETPOLINE_LFENCE	(11*32+13) /* "" Use LFENCE for Spectre variant 2 */
 #define X86_FEATURE_RETHUNK		(11*32+14) /* "" Use REturn THUNK */
 #define X86_FEATURE_UNRET		(11*32+15) /* "" AMD BTB untrain return */
+#define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM-Exit when EIBRS is enabled */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
 #define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index ec2967e7249f..8f38265bc81d 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -148,6 +148,10 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#define ARCH_CAP_PBRSB_NO		BIT(24)	/*
+						 * Not susceptible to Post-Barrier
+						 * Return Stack Buffer Predictions.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e2c8f946c541..8330e3ca8fbf 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5347,7 +5347,8 @@ struct bpf_sock {
 	__u32 src_ip4;
 	__u32 src_ip6[4];
 	__u32 src_port;		/* host byte order */
-	__u32 dst_port;		/* network byte order */
+	__be16 dst_port;	/* network byte order */
+	__u16 :16;		/* zero padding */
 	__u32 dst_ip4;
 	__u32 dst_ip6[4];
 	__u32 state;
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 5a5bd74f55bd..9c366b3a676d 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -1646,7 +1646,8 @@ Press any other key to refresh statistics immediately.
                          .format(values))
             if len(pids) > 1:
                 sys.exit('Error: Multiple processes found (pids: {}). Use "-p"'
-                         ' to specify the desired pid'.format(" ".join(pids)))
+                         ' to specify the desired pid'
+                         .format(" ".join(map(str, pids))))
             namespace.pid = pids[0]
 
     argparser = argparse.ArgumentParser(description=description_text,
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index 577d619fb07e..197ec1d1b702 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -1,9 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 
+#define _GNU_SOURCE
 #include <netinet/in.h>
 #include <arpa/inet.h>
 #include <unistd.h>
+#include <sched.h>
 #include <stdlib.h>
 #include <string.h>
 #include <errno.h>
@@ -21,6 +23,7 @@
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
 	INGRESS_LINUM_IDX,
+	READ_SK_DST_PORT_LINUM_IDX,
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
@@ -43,8 +46,16 @@ static __u64 child_cg_id;
 static int linum_map_fd;
 static __u32 duration;
 
-static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
-static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
+static bool create_netns(void)
+{
+	if (!ASSERT_OK(unshare(CLONE_NEWNET), "create netns"))
+		return false;
+
+	if (!ASSERT_OK(system("ip link set dev lo up"), "bring up lo"))
+		return false;
+
+	return true;
+}
 
 static void print_sk(const struct bpf_sock *sk, const char *prefix)
 {
@@ -92,19 +103,24 @@ static void check_result(void)
 {
 	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
 	struct bpf_sock srv_sk, cli_sk, listen_sk;
-	__u32 ingress_linum, egress_linum;
+	__u32 idx, ingress_linum, egress_linum, linum;
 	int err;
 
-	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
-				  &egress_linum);
+	idx = EGRESS_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &egress_linum);
 	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
-	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
-				  &ingress_linum);
+	idx = INGRESS_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &ingress_linum);
 	CHECK(err < 0, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d\n", err, errno);
 
+	idx = READ_SK_DST_PORT_LINUM_IDX;
+	err = bpf_map_lookup_elem(linum_map_fd, &idx, &linum);
+	ASSERT_OK(err, "bpf_map_lookup_elem(linum_map_fd, READ_SK_DST_PORT_IDX)");
+	ASSERT_EQ(linum, 0, "failure in read_sk_dst_port on line");
+
 	memcpy(&srv_sk, &skel->bss->srv_sk, sizeof(srv_sk));
 	memcpy(&srv_tp, &skel->bss->srv_tp, sizeof(srv_tp));
 	memcpy(&cli_sk, &skel->bss->cli_sk, sizeof(cli_sk));
@@ -263,7 +279,7 @@ static void test(void)
 	char buf[DATA_LEN];
 
 	/* Prepare listen_fd */
-	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	listen_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0xcafe, 0);
 	/* start_server() has logged the error details */
 	if (CHECK_FAIL(listen_fd == -1))
 		goto done;
@@ -331,8 +347,12 @@ done:
 
 void test_sock_fields(void)
 {
-	struct bpf_link *egress_link = NULL, *ingress_link = NULL;
 	int parent_cg_fd = -1, child_cg_fd = -1;
+	struct bpf_link *link;
+
+	/* Use a dedicated netns to have a fixed listen port */
+	if (!create_netns())
+		return;
 
 	/* Create a cgroup, get fd, and join it */
 	parent_cg_fd = test__join_cgroup(PARENT_CGROUP);
@@ -353,15 +373,20 @@ void test_sock_fields(void)
 	if (CHECK(!skel, "test_sock_fields__open_and_load", "failed\n"))
 		goto done;
 
-	egress_link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields,
-						 child_cg_fd);
-	if (!ASSERT_OK_PTR(egress_link, "attach_cgroup(egress)"))
+	link = bpf_program__attach_cgroup(skel->progs.egress_read_sock_fields, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(egress_read_sock_fields)"))
+		goto done;
+	skel->links.egress_read_sock_fields = link;
+
+	link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(ingress_read_sock_fields)"))
 		goto done;
+	skel->links.ingress_read_sock_fields = link;
 
-	ingress_link = bpf_program__attach_cgroup(skel->progs.ingress_read_sock_fields,
-						  child_cg_fd);
-	if (!ASSERT_OK_PTR(ingress_link, "attach_cgroup(ingress)"))
+	link = bpf_program__attach_cgroup(skel->progs.read_sk_dst_port, child_cg_fd);
+	if (!ASSERT_OK_PTR(link, "attach_cgroup(read_sk_dst_port"))
 		goto done;
+	skel->links.read_sk_dst_port = link;
 
 	linum_map_fd = bpf_map__fd(skel->maps.linum_map);
 	sk_pkt_out_cnt_fd = bpf_map__fd(skel->maps.sk_pkt_out_cnt);
@@ -370,8 +395,7 @@ void test_sock_fields(void)
 	test();
 
 done:
-	bpf_link__destroy(egress_link);
-	bpf_link__destroy(ingress_link);
+	test_sock_fields__detach(skel);
 	test_sock_fields__destroy(skel);
 	if (child_cg_fd >= 0)
 		close(child_cg_fd);
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields.c b/tools/testing/selftests/bpf/progs/test_sock_fields.c
index 7967348b11af..43b31aa1fcf7 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields.c
@@ -12,6 +12,7 @@
 enum bpf_linum_array_idx {
 	EGRESS_LINUM_IDX,
 	INGRESS_LINUM_IDX,
+	READ_SK_DST_PORT_LINUM_IDX,
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
@@ -250,4 +251,48 @@ int ingress_read_sock_fields(struct __sk_buff *skb)
 	return CG_OK;
 }
 
+static __noinline bool sk_dst_port__load_word(struct bpf_sock *sk)
+{
+	__u32 *word = (__u32 *)&sk->dst_port;
+	return word[0] == bpf_htonl(0xcafe0000);
+}
+
+static __noinline bool sk_dst_port__load_half(struct bpf_sock *sk)
+{
+	__u16 *half = (__u16 *)&sk->dst_port;
+	return half[0] == bpf_htons(0xcafe);
+}
+
+static __noinline bool sk_dst_port__load_byte(struct bpf_sock *sk)
+{
+	__u8 *byte = (__u8 *)&sk->dst_port;
+	return byte[0] == 0xca && byte[1] == 0xfe;
+}
+
+SEC("cgroup_skb/egress")
+int read_sk_dst_port(struct __sk_buff *skb)
+{
+	__u32 linum, linum_idx;
+	struct bpf_sock *sk;
+
+	linum_idx = READ_SK_DST_PORT_LINUM_IDX;
+
+	sk = skb->sk;
+	if (!sk)
+		RET_LOG();
+
+	/* Ignore everything but the SYN from the client socket */
+	if (sk->state != BPF_TCP_SYN_SENT)
+		return CG_OK;
+
+	if (!sk_dst_port__load_word(sk))
+		RET_LOG();
+	if (!sk_dst_port__load_half(sk))
+		RET_LOG();
+	if (!sk_dst_port__load_byte(sk))
+		RET_LOG();
+
+	return CG_OK;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index ce13ece08d51..8c224eac93df 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -121,7 +121,25 @@
 	.result = ACCEPT,
 },
 {
-	"sk_fullsock(skb->sk): sk->dst_port [narrow load]",
+	"sk_fullsock(skb->sk): sk->dst_port [word load] (backward compatibility)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [half load]",
 	.insns = {
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
@@ -139,7 +157,64 @@
 	.result = ACCEPT,
 },
 {
-	"sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]",
+	"sk_fullsock(skb->sk): sk->dst_port [half load] (invalid)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [byte load]",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port)),
+	BPF_LDX_MEM(BPF_B, BPF_REG_2, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = ACCEPT,
+},
+{
+	"sk_fullsock(skb->sk): sk->dst_port [byte load] (invalid)",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	.result = REJECT,
+	.errstr = "invalid sock access",
+},
+{
+	"sk_fullsock(skb->sk): past sk->dst_port [half load] (invalid)",
 	.insns = {
 	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
@@ -149,7 +224,7 @@
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
-	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, dst_port)),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index e0b0164e9af8..be1d9728c4ce 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -73,20 +73,19 @@ void ucall_uninit(struct kvm_vm *vm)
 
 void ucall(uint64_t cmd, int nargs, ...)
 {
-	struct ucall uc = {
-		.cmd = cmd,
-	};
+	struct ucall uc = {};
 	va_list va;
 	int i;
 
+	WRITE_ONCE(uc.cmd, cmd);
 	nargs = nargs <= UCALL_MAX_ARGS ? nargs : UCALL_MAX_ARGS;
 
 	va_start(va, nargs);
 	for (i = 0; i < nargs; ++i)
-		uc.args[i] = va_arg(va, uint64_t);
+		WRITE_ONCE(uc.args[i], va_arg(va, uint64_t));
 	va_end(va);
 
-	*ucall_exit_mmio_addr = (vm_vaddr_t)&uc;
+	WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc);
 }
 
 uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index e0b2bb1339b1..3330fb183c68 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -44,7 +44,7 @@ static inline void nop_loop(void)
 {
 	int i;
 
-	for (i = 0; i < 1000000; i++)
+	for (i = 0; i < 100000000; i++)
 		asm volatile("nop");
 }
 
@@ -56,12 +56,14 @@ static inline void check_tsc_msr_rdtsc(void)
 	tsc_freq = rdmsr(HV_X64_MSR_TSC_FREQUENCY);
 	GUEST_ASSERT(tsc_freq > 0);
 
-	/* First, check MSR-based clocksource */
+	/* For increased accuracy, take mean rdtsc() before and afrer rdmsr() */
 	r1 = rdtsc();
 	t1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	r1 = (r1 + rdtsc()) / 2;
 	nop_loop();
 	r2 = rdtsc();
 	t2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT);
+	r2 = (r2 + rdtsc()) / 2;
 
 	GUEST_ASSERT(r2 > r1 && t2 > t1);
 
@@ -181,12 +183,14 @@ static void host_check_tsc_msr_rdtsc(struct kvm_vm *vm)
 	tsc_freq = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TSC_FREQUENCY);
 	TEST_ASSERT(tsc_freq > 0, "TSC frequency must be nonzero");
 
-	/* First, check MSR-based clocksource */
+	/* For increased accuracy, take mean rdtsc() before and afrer ioctl */
 	r1 = rdtsc();
 	t1 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	r1 = (r1 + rdtsc()) / 2;
 	nop_loop();
 	r2 = rdtsc();
 	t2 = vcpu_get_msr(vm, VCPU_ID, HV_X64_MSR_TIME_REF_COUNT);
+	r2 = (r2 + rdtsc()) / 2;
 
 	TEST_ASSERT(t2 > t1, "Time reference MSR is not monotonic (%ld <= %ld)", t1, t2);
 
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 9b68658b6bb8..5b98f3ee58a5 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -233,6 +233,24 @@ static unsigned long read_slab_obj(struct slabinfo *s, const char *name)
 	return l;
 }
 
+static unsigned long read_debug_slab_obj(struct slabinfo *s, const char *name)
+{
+	char x[128];
+	FILE *f;
+	size_t l;
+
+	snprintf(x, 128, "/sys/kernel/debug/slab/%s/%s", s->name, name);
+	f = fopen(x, "r");
+	if (!f) {
+		buffer[0] = 0;
+		l = 0;
+	} else {
+		l = fread(buffer, 1, sizeof(buffer), f);
+		buffer[l] = 0;
+		fclose(f);
+	}
+	return l;
+}
 
 /*
  * Put a size string together
@@ -409,14 +427,18 @@ static void show_tracking(struct slabinfo *s)
 {
 	printf("\n%s: Kernel object allocation\n", s->name);
 	printf("-----------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "alloc_calls"))
+	if (read_debug_slab_obj(s, "alloc_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "alloc_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");
 
 	printf("\n%s: Kernel object freeing\n", s->name);
 	printf("------------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "free_calls"))
+	if (read_debug_slab_obj(s, "free_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "free_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");